There has been extensive work in the last few decades on tranformational spaces within the realm of music analysis. This has been applied to both pitch transformations and also extended to triadic transformations. Given this, it is possible to create 2-dimensional graphs of triadic transformational spaces which can be used to describe the transitions of a particular piece. Based on that concept, I built a software tool that will iterate through all possible 2D graphs, and find the shortest path for each transition in a piece, allowing the user to find the most efficient transformational space for that piece.
This research explores the use of an extended probabilistic model such as the Hidden Semi-Markov Model (HSMM) to approach the task of automatic harmonization. One distinct advantage of the HSMM is that it is able to automatically differentiate harmonic boundaries, through its inclusion of an extra parameter: duration. In this way, a melody can be harmonized automatically in the style of a particular corpus. In the case of this research, the corpus was in the style of Rock 'n' Roll.
It was presented at the 2013 Workshop on Musical Metacreation, as part of the Conference on Artificial Intelligence In Digital Entertainment
Presented original work regarding a system which generates chord progressions in the style of Rock 'n' Roll. The research was presented as both a poster session and a 5-minute oral presentation as part of the 2013 Mathematics and Computation in Music Conference.
This research distilled the rules of classical counterpoint and applied them to the generation of popular music melodies. The system analyzes a melody, and, based on its chord progression, makes decisions to move notes up or down in pitch in order to create a more consonant melodic sequence.
A system and process for producing a more harmonious musical accompaniment for a musical compilation, the process comprising determining a plurality of probable key signatures for the musical compilation, creating an interval profiling matrix for each of the probable key signatures, finding products of a major key interval profile matrix with each of the interval profiling matrices, summing each of the major key interval products into a running major key sum, finding a product of a minor key interval profile with each of the interval profiling matrices, summing each of the minor key interval products into a running minor key sum, and selecting the most probable key signature from the plurality of probable key signatures by comparing the minor key sum and the major key sum.
A dynamic system which conforms the underlying harmony to the rules of harmonic progression while simultaneously creating consonance with the input monophonic vocal melody.
A set of algorithms that both detects key signature in a monophonic vocal melody, and makes the musical corrections necessary to snap all the notes of the sung melody into the appropriate key signature.